US 11,914,093 B2
RF antenna scanning for human movement classification
Jouya Jadidian, Los Gatos, CA (US); Emily Po-Kay Chung, Mountain View, CA (US); and James Chester Meador, Mountain View, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Dec. 7, 2021, as Appl. No. 17/643,141.
Prior Publication US 2023/0176243 A1, Jun. 8, 2023
Int. Cl. G01V 3/08 (2006.01); G01V 3/38 (2006.01); G06F 3/01 (2006.01)
CPC G01V 3/088 (2013.01) [G01V 3/38 (2013.01); G06F 3/012 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method for human movement classification, comprising:
at a computing device, driving each of a plurality of RF (radio frequency) antennas to expose a body surface of a human user to an E-field, wherein at least part of a face of the human user is positioned within a near-field region relative to the plurality of RF antennas;
scanning each of the plurality of RF antennas to individually determine ground-relative changes in electrical conditions for each of the plurality of RF antennas relative to a previous time frame;
selecting a differential-scanning subset of RF antennas from among the plurality of RF antennas, including two or more RF antennas for which the ground-relative changes in electrical conditions exceed a frame-to-frame threshold;
for each RF antenna in the differential-scanning subset, determining a set of antenna-relative changes in electrical conditions by comparing the RF antenna to one or more other RF antennas in the differential-scanning subset as a plurality of pairs; and
based at least in part on the ground-relative changes in electrical conditions and the antenna-relative changes in electrical conditions, classifying a movement performed by the human user as a recognized facial expression of a plurality of predefined facial expressions.